smh
I implemented my own unimo network and use triplet as CMCL loss. The text cls outputs in same batch were set as negative samples corresponding to positive image-text pair, but...
I use my own image datas with `demo.py` and got this error, no any other infos display. I have located the postion causing this error, its [roi layer calling](https://github.com/NVlabs/STEP/blob/59da38af240869fa6f1bc565803cff34aafdaa99/external/maskrcnn_benchmark/roi_layers/roi_align.py#L53). However,...
https://github.com/qfgaohao/pytorch-ssd/blob/1e86eb3a9655ca1893b537829bbbc2794614d485/vision/utils/box_utils.py#L36 If the centers of prior box are relative to image size, so the `division` to scale should be changed to multiplied by `scale` ??? I have not yet verify...
I ran the tensorrt code on Tesla V100 (TensorRT 5.1.2.2, CUDA10.1) and K40 (TensorRT 4.0.1.6, CUDA 8.0), and got different results on a few images. Would you please give me...
Or, can I convert the test image from sRGB color space to ProPhoto RGB color space for inference ?
According to my understanding, the permute order should be (2, 0, 1) but not (2, 1, 0), otherwise, the mul(a, v) calculation may have transposed position correspondings.  Please correct...
Hi fchollet, Now, I'm using vgg16 under Keras to classify oxford 102 flower dataset and I want to download the trained weight file: vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5. But I cannot download it... Wourld...
I download the dataset from this [link](https://www.dropbox.com/s/wpx6tqjf0y5mf6r/faces_ms1m-refine-v2_112x112.zip?dl=0), the downloaded file is named as `faces_ms1m-refine-v2_112x112.zip`. However I got the `face_emore` folder name after unzip that file, and the `property` file from...